A random mix from the whole library. Shuffle for a new set.
Creator Amie Tollefsrud gave the AI access to her Instagram analytics and asked for growth advice; after three clarifying questions about audience and positioning, the AI delivered an 'Instagram Growth Plan' PDF. Screen recordings show an executive diagnosis (1.85M accounts reached), audience positioning, four content pillars, keyword clusters, carousel and story blueprints, and a 7-day action checklist.
Opus 5.5 built an imapsync wrapper used for a week-long migration of 5.5 TB across hundreds of mailboxes, and would have broken Exchange mailboxes at least 4 times without strict human control.
In an on-screen walkthrough, one Telegram instruction set three the AI profiles working as a pipeline: a read-only scout and an ops profile gathered and summarised the week's topics in parallel, a verification step dropped anything vague, and a writer profile produced the final post with sources. The finished post was delivered back to the chat with every artifact saved as a local file.
A man who flips vintage items on eBay connected the AI to his store. The AI found 28 listings with views but no sales, worked out that eBay was really taking 16% in fees, and published a bundle of two vases that sold within a week.
Used the AI to build an omit needless words app and used it to edit a document he is working on, accepting about a third of its suggestions.
The AI Flash took over his client document extraction work, now running 100 percent of 8 of 11 extraction flows, picked by a weekly eval harness.
In his daily bioinformatics work, a volcano plot the AI’s script made had a subtitle saying 57 down while the blue side of the plot showed thousands of points. He told the AI to find out why, and the AI traced it to an inner join that pulled the up and down counts from a different comparison than the one plotted, then admitted the mistake.
A client needed a small design job that would have taken him hours. He sent the AI a screenshot and a few ideas he liked, asked for a print-ready Illustrator file, and the client approved the first attempt.
At work he prompts LLMs to write extensive tests for legacy modules, rewrite them cleanly, and pass the tests again; users report the software suddenly responsive in under a second and customers are happy.
He had wanted an automatic provisioner for his boards for a long time but it was a whole project on its own, so he told the AI to write it. Some physical steps still need him, but each board now takes 2 to 3 minutes instead of a few stressful hours.
Every idea is a real post from someone who tried it, summarized in our words, with a link to the original. App names are swapped for plain words.